TI-StegoAlign: Channel-Guided Post-Training for Generative Text Steganography under Tokenization Inconsistency

Computer Science > Cryptography and Security [Submitted on 1 Aug 2026] TI-StegoAlign: Channel-Guided Post-Training for Generative Text Steganography under Tokenization Inconsistency Jiuan Zhou, Yuhao Xue, Yu Cheng, Yuan Xie, Zhaoxia Yin Generative text steganography enables LLM agents to exchange secret information through task-relevant messages. Yet most methods evaluate recovery on sender-side tokens, whereas the receiver observes only surface text. Detokenization and receiver-side retokenization can alter token boundaries, desynchronize coding states, and cause such evaluation to overestimate receiver-side recovery. Existing remedies rely on inference-time filtering or verification, correcting individual outputs without adapting the generation policy to the receiver-side channel. To address these limitations, we propose TI-StegoAlign, a channel-guided post-training framework. The Bit-Consistent Supervised Objective (BCSO) enlarges local coding margins at realized sender-side embedding positions. Channel-Conditioned Preference Optimization (CCPO) then aligns complete stegotexts using receiver-realistic recovery, text quality, and anti-steganalysis feedback. TI-StegoAlign updates only LoRA parameters and requires no tokenization-specific correction during communication. Experimental results show 100% receiver bit accuracy. Compared with the strongest baselines, TI-StegoAlign achieves a 21.6% reduction in normalized perplexity deviation and a 6.3% relative improvement in anti-steganalysis performance. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2608.00382 [cs.CR]   (or arXiv:2608.00382v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.00382 Focus to learn more Submission history From: Jiuan Zhou [view email] [v1] Sat, 1 Aug 2026 01:45:50 UTC (382 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)